Waste Object Segmentation with state of art algorithm YOVOv5 trained on Custom Dataset.
Here I address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. Specifically, our method integrates the intensity and depth information at multiple levels of spatial granularity. Firstly, a scene-level deep network produces an initial coarse segmentation, based on which we select a few potential object regions to zoom in and perform fine segmentation.
I have tranied multiple YOLOv5 model check the model validation states..
| 
| 
|
To evaluate object detection models like R-CNN and YOLO, the mean average precision (mAP) is used. which is around 95% with this perticular dataset..
| 
| 
|
Due to less amount of data here i have trained yolov5 for only 8 class detection and confusion matrix for best model from tranied models so far look as below
